Gadgets for fitness, in particular wearable sensors, have motivated how we exercise but may not always capture all exercises equally—as recent research at Carnegie Mellon University suggests. In fact, researchers have found that that a stationary camera is a better option for gym exercises than something like a smartwatch.
The camera used in the study is a vision-based system referred to as ‘GymCam’ and works by capturing repetitive motions which could recognize the particular type of exercise and reliably count repetitions. "In a gym, the repetitive motion almost always is an exercise," said Mayank Goel, assistant professor in the HCII and Institute for Software Research. "If you are moving both your arms, you tend to move them together in time. However, if two people are exercising next to each other and performing the same exercise, they are usually not in sync, and we can tell the difference between them."
GymCam only detects motion information which can be decreased to a pixel-by-pixel changes and eliminate identifiable faces for privacy reasons. GymCam is unique in that it can detect exercise as long as the camera can see any body part moving repetitively. Although smartwatches and other wearables are effective—that effectiveness is dependent on the tracking of many cardio exercises and some strength-training exercises placed in specific regions of the body. For example, a smartwatch can sense a dumbbell lift but not leg presses.
GymCam can also learn the location of different types of exercise machines and/or certain stations in a gym and can also be used beyond physical exercise. For example, the system can assist individuals with visual disabilities in navigation in areas like airports and shopping malls. Other companies have noted that the system can also be implemented for tracking in-home exercises.
Source: Science Daily